Evaluating AI Methods for Pulse Oximetry: Performance, Clinical Accuracy, and Comprehensive Bias Analysis

Blood oxygen saturation (SpO ) is vital for patient monitoring, particularly in clinical settings. Traditional SpO estimation methods have limitations, which can be addressed by analyzing photoplethysmography (PPG) signals with artificial intelligence (AI) techniques. This systematic review, following PRISMA guidelines, analyzed 183 unique references from WOS, PubMed, and Scopus, with 26 studies meeting the inclusion criteria. The review examined AI models, key features, oximeters used, datasets, tested saturation intervals, and performance metrics while also assessing bias through the QUADAS-2 criteria. Linear regression models and deep neural networks (DNNs) emerged as the leading AI methodologies, utilizing features such as statistical metrics, signal-to-noise ratios, and intricate waveform morphology to enhance accuracy. Gaussian Process models, in particular, exhibited superior performance, achieving Mean Absolute Error (MAE) values as low as 0.57% and Root Mean Square Error (RMSE) as low as 0.69%. The bias analysis highlighted the need for better patient selection, reliable reference standards, and comprehensive SpO intervals to improve model generalizability. A persistent challenge is the reliance on non-invasive methods over the more accurate arterial blood gas analysis and the limited datasets representing diverse physiological conditions. Future research must focus on improving reference standards, test protocols, and addressing ethical considerations in clinical trials. Integrating AI with traditional physiological models can further enhance SpO estimation accuracy and robustness, offering significant advancements in patient care.